Professional Documents
Culture Documents
Morrison 1979
Morrison 1979
Your use of the JSTOR archive indicates your acceptance of the Terms & Conditions of Use, available at .
http://www.jstor.org/page/info/about/policies/terms.jsp
.
JSTOR is a not-for-profit service that helps scholars, researchers, and students discover, use, and build upon a wide range of
content in a trusted digital archive. We use information technology and tools to increase productivity and facilitate new forms
of scholarship. For more information about JSTOR, please contact support@jstor.org.
American Marketing Association is collaborating with JSTOR to digitize, preserve and extend access to
Journal of Marketing.
http://www.jstor.org
PURCHASE
INTENTIONS
AND PURCHASE
BEHAVIOR
Journal of Marketing
Vol. 43 (Spring 1979), 65-74. Purchase Intentionsand Purchase Behavior/ 65
TABLE 1
Automobiles: 6 and 12 Month Intentions vs. 6 Month Purchases
a=.12, 1,
= .56 /,=.17 p =.22, b= 0
period-December 1964 to June 1965. Yet, he used matedby a simple regressionof intentionversus actual
these same purchasedata for assessing six, 12, and 24 purchaseprobabilityfor the intentiongroup.2When the
monthintentions.Whenthe 12 and24 monthintentions S1, 2, and 3} groupwas used, the middlevalueof 2 was
are compared to six month purchases we seem to be the value used in the regression,and similarlyfor {4, 5,
comparing apples to oranges. However, as the au- and 6} and {7, 8, and 9}. The bias is, of course, the
tomobile data will show there is some advantage to difference between the mean intention and the total
doing these differing time frame comparisons. sample purchaseproportion.Finally, some of the pur-
Table 1 gives the results for automobiles. The chase data were not collected so that the two sample
sample histogramfor both six and 12 month intentions sizes differ somewhat. Justerdoesn't explain why he
arepresented.The numbersin parenthesesarethe fitted kept some of the intentiondatathathad no correspond-
beta binomial expected values (roundedto the nearest ing purchase data. In any event we had no way of
integer). The beta binomial parametersa and /3 are correcting this difference.
estimated by the method of moments while p is esti- Table 2 contains analogous results for six house-
hold appliances (air conditioners, refrigerators,wash-
2Scalingthe statedintentions0, 1 10 the samplemean,X, andsample
variance.S2, of these intentionsare....
calculated. We then solve for the values ing machines, clothes dryers, television sets, and dish-
a and /3 that make the theoreticalmean 10l/(a+/P)=X and the theoretical washers). Juster does not present data for the indi-
variance lOaJp(a+p+ 1O)/(a+)2(a+p+ 1)=S2. The theoreticalslope of vidual appliances. That is, each individualrepresents
actual purchase probability versus stated intentions is (l-p)/(a+P3+1).
Since we previously calculated a and 8 we now find p which makes the six datapoints-an intention, purchasepair for each of
observedslope equal (l-p)/(a++3 1). the six appliances. In addition, only 12 and 24 month
TABLE3
SummaryStatistics
Category Time a 1 p b
/
Frame 1+a+P
Automobile 6 months .074 .67
.57-.071
Automobile 12 months .120 .56 .60 0
Appliances 12 months .034 .58 .021
.691
Appliances 24 months .050 .51 .64 .79 1 .064
.74